Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

AWS ML Exam > Sagemaker Built-in Algorithms > Flashcards

Sagemaker Built-in Algorithms Flashcards

1
Q

Linear Learner

A

linear regression
can handle both regression and classification
for classification, a linear threshold is used

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Linear Learner Input Format

A

recordIO/protobuf, csv

file or pipe mode supported

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Linear Learner Usage

A 
preprocessing:
data must be normalized and shuffled
training:
choose optimization function alg
multiple models optimized in parallel
tune L1, L2 regularization
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

XGBoost

A

eXtreme Gradient Boosting
boosted group of decision trees
gradient descent to minimize loss
can be used for classification and regression

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

XGBoost Input

A

CSV, libsvm

recently recordIO/protobuf, Parquet

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

XGBoost Usage

A

Models are serialized/deserialized with Pickle
can be used within notebook or as a built in SM algorithm

HPs: Subsample, eta, gamma, alpha, lambda

Only uses CPUs, only memory bound

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Seq2Seq

A

Input is a sequence of tokens, output is a sequence of tokens
good for machine translation, text summarization, speech to text

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Seq2Seq Input

A

recordIO/protobuf - tokens must be integers
start with tokenized text files
NEED TO PROVIDE TRAINING DATA, VALIDATION DATA, AND VOCAB FILES

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Seq2Seq Usage

A

Training can take days
Pretrained models available
Public training datasets available for specific translation tasks

HPs: batch, optimizer, # layers
can optimize on accuracy, BLEU score, perplexity

only uses single machine GPU

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

DeepAR

A

forcasting 1D time-series data
uses RNNs
allows you to train the same model on several related time series
finds frequency and seasonality

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

DeepAR Input

A

JSON lines (gzip or parquet)
each record must contain: start, target
can contain dynamic/categorical features

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

DeepAR Usage

A
  • always include entire time series
  • uses entire dataset, remove last points for training
  • don’t use very large values for prediction length
  • train on many time series’ when possible

HPs: epochs, batch size, learning rate, # cells, context length

GPU or CPU for training, CPU only for inference

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

BlazingText

A
  1. Text Classification
    predict labels for a sentence (NOT DOCS)
    supervised
    ex. web search, info retrieval
  2. Word2Vec
    - vector representation of words
    - semantically similar words represented by vectors
    close to each other > word embedding
    - useful for NLP, but not an NLP algorithm
    - only works on INDIVIDUAL words
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

BlazingText Input

A
  1. Text Class. (supervised mode)
    - 1 sentence / line
    - 1st word in sentence is label “label”
    - augmented manifest text format
  2. Word2Vec
    - text file with 1 sentence / line
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

BlazingText Usage

A

Word2Vec has multiple modes:

- cbow > continuous bag of words (order doesn't matter)
- skip-gram (order matters)
- batch skip-gram (distributed over CPU nodes)

HPs:

  • Word2Vec: mode, learning rate, window size, vector dim, negative samples
  • Text Classification: epochs, learning rate, word n-grams, vector dim (how many words we look at together)

cbow and skipgram use GPU (can use CPU)
batch skipgram use single or multiple CPU
Text class - use CPU for smaller, GPU for larger

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Object2Vec

A
  • like Word2Vec but with arbitrary objects
  • boil data down to lower level representation
    • compute nearest neighbors, visualize clusters, genre prediction, recommendations
  • UNSUPERVISED
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Object2Vec Input

A
  • tokenized into integers
  • pairs or sequences of tokens
    • sentence-sentence, labels-sequence, customer-customer, product-product, user-item
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

Object2Vec Usage

A
  • process data into JSON and shuffle
  • train with 2 input channels, 2 encoders, 1 comparator
  • encoder choices:
    • average pooled embeddings, CNN, bidirectional LSTM
  • comparator is followed by a feed-forward neural network

HPs: usual deep learning ones:

- dropout, early stopping, epochs, learning rate, batch size, layers, activation function, optimizer, weight decay - encoder1 network, encoder2 network

single machine, multi GPU
use inference pref mode to optimize for encoder embeddings rather than classification or regression

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Object Detection

A
  • ID all images in an image with bounding boxes
  • detect and classify with one deep neural network
    • provide confidence scores
  • can train images from scratch, or use pretrained models on ImageNet
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

Object Detection Input

A
  • recordIO or image format (need JSON file for annotation data)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

Object Detection Usage

A
  • image&raquo_space; outputs all instances of all objects in image with categories and confidence scores
  • CNN with SSD algorithm
    • VGG-16 or ResNet 50
  • transfer learning mode / incremental training
    • use pretrained model for base network weights instead of random initial rates
  • uses flip, rescale, and jitter to avoid overfitting

HPs: batch size, learning rate, optimizer

GPU for training, CPU for inference

22
Q

Image Classification

A
  • assign one or more labels to an image

- doesn’t tell you where the objects are (no bounding)

23
Q

Image Classification Input

A
  • MxNet Record10 (not protobuf!)
  • raw images
    • requires first file to associate image with labels
  • augmented manifest image format - pipe mode!
24
Q

Image Classification Usage

A
  • ResNet CNN
  • full training > initialized with random weights
  • transfer learning mode:
    • initialized with pretrained weights
    • top layer is initialized with random weights
    • network is fine-tuned with new training data
  • default size is 3channel 224*224

HPs: batch, learning rate, optimizers (weight decay, beta1, beta2, eps, gamma)

GPU for training, GPU or CPU for instance

25
Q

Semantic Segmentation

A
  • pixel-level object classification
  • useful for self-driving cars
  • produces a segmentation mask
26
Q

Semantic Segmentation Input

A
  • JPG images and PNG annotations
  • label maps for describing annotations
  • augmented manifest image format for pipe!
  • JPG for inference
27
Q

Semantic Segmentation Usage

A
  • built on MxNet Gluon and GluonCV
  • choice of 3 algorithms:
    • fully-convolutional network (FCN)
    • pyramid scene parsing (PSP)
    • DeepLabV3
  • backbone: ResNet50, ResNet10
    • both trained on ImageNet

HPs: epochs, learning rate, batch size, optimizer, algorithm used, backbone used

single machine GPU only, CPU or GPU for inference

28
Q

Random Cut Forest

A
  • unsupervised anomaly detection
  • detect
    • spikes in time-series data
    • breaks in periodicity
    • unclassifiable data points
  • gives anomaly score to each point
  • amazon very proud of this!
29
Q

Random Cut Forest Inputs

A
  • CSV or recordIO/protobuf
  • file or pipe
  • optional test channel for computing AUC, recall, precision, F1 score
30
Q

Random Cut Forest Usage

A
  • create forest of trees where each tree is a partition of the training data
  • looks at expected change in complexity as a result of adding a new point
  • sampled randomly, then trained
  • can be used on time series

HPs: number of trees (increasing # reduces noise), samples / tree

no GPU

31
Q

Neural Topic Model

A
  • organize documents into topics
  • classify/summarize documents based on topics
  • not just TF/IDF
    • NTM groups things into higher levels
  • unsupervised
    • uses a neural variational inference algorithm
32
Q

Neural Topic Model Input

A
  • four data channels
    • train channel required (validation, test, aux optional)
  • recordIO/protobuf or CSV
  • words need to be tokenized with a vocab file
  • file or pipe mode
33
Q

Neural Topic Model Usage

A
  • define how many topics to generate
  • latent representation based on top-ranking words
  • one of two topic modeling algorithms (LDA)

HPs: smaller batch size and learning rate can reduce validation loss but increase training time, # of topics

CPU or GPU

34
Q

Latent Dirichlet Allocation (LDA)

A
  • topic modeling (not deep learning)
  • unsupervised
    • grouping of documents with shared subset of words
  • can be used for things other than words
    • customer clusters, harmonic analysis
35
Q

LDA Input

A
  • train, optional test channel
  • recordIO/protobuf or CSV - need to tokenize
  • each document has counts for every word in vocab (CSV)
  • pipe only supported with recordIO
36
Q

LDA Usage

A
  • unsupervised > you pick the # of topics
  • test channel - score results
  • functionally similar to Neural Topic Modeling, but CPU based

HPs: # of topics, Alpha0 (initial guess for concentration values)

single instance CPU

37
Q

KNN

A
  • supervised
  • simple classification or regression algorithm
  • classification:
    • find K closest points to a sample and return most frequent label
  • regression:
    • find K closest points to a sample and return average value
38
Q

KNN Input

A
  • train, optional test channel
  • recordIO/protobuf or CSV
  • file or pipe
39
Q

KNN Usage

A
  • data is sampled
  • dimensionality reduction
    • avoid sparse data at the cost of noise/accuracy
    • sign or figit methods
  • build index
  • serialize
  • query

HPs: K, sample size

CPU or GPU
inference - CPU for lower latency, GPU for higher throughput

40
Q

K-Means

A
  • unsupervised clustering
  • divide data into K groups where members are similar
    • you define “similar” > euclidian distance
  • web-scale k-means clustering
41
Q

K-means Inputs

A
  • train channel (sharded by S3 key flag), optional test (fully replicated key flag)
  • recordIO/protobuf or CSV
  • file and pipe
42
Q

K-Means Usage

A
  • every observation mapped to n-dimensional space
  • works to optimize center of K-clusters
    • extra cluster centers may be specified to improve accuracy
    • K = k*x
      • k = clusters we want
      • x = extra cluster centers
  • algorithm: determine initial cluster centers
    • random or K-means ++
      • K-means ++ tries to make initial clusters far apart
  • iterate over data and calculate cluster centers
  • reduce clusters from K to k (using Lloyd’s method for k-means++)

HPs: batch size, extra center factor (x), init method (random or k-means++), K
- K is tricky: use elbow method - basically optimize for tightness of clusters

CPU or GPU (CPU recommended)

43
Q

Principal Component Analysis (PCA)

A
  • dimensionality reduction
    • projecting higher-level dimensional data into lower-dimensional (like a 2D plot) while minimizing loss of info
  • reduced dimensions are called components
    • first component has largest possible variability
    • 2nd component has next largest
  • unsupervised
44
Q

PCA Inputs

A
  • recordIO/protobuf

- file or pipe

45
Q

PCA Usage

A
  • covariance matrix created, then singular value decomposition (SVD)
  • 2 modes:
    • regular - sparse data, moderate # of features
    • randomized - large # of features
      • uses approximation algorithm

HPs: algorithm mode, subtract mean (unbias data)

CPU or GPU - depends on specifics of data

46
Q

Factorization Machines

A
  • classification/regression with SPARSE DATA
  • good for recommendations
    • click prediction
    • item recommendations
    • since a user doesn’t interact with most pages/products, the data is sparse
  • supervised (classification or regression)
  • limited to pair-wise interactions
    • user - item
47
Q

Factorization Machines Inputs

A
  • recordIO/protobuf with Float32

- sparse data means CSV isn’t practical

48
Q

Factorization Machines Usage

A
  • essentially makes a big matrix
  • find factors we can use to predict a classification (click or not) or value (predicted rating) given a matrix representing some pair of things (users and items)

HPs: initialization methods for bias, factors, and linear terms
- uniform, normal, or constant

CPU or GPU - CPU recommended, GPU only works with dense data

49
Q

IP Insights

A
  • unsupervised
  • learning of IP address usage patterns
    • ID suspicious activity
    • security tool
50
Q

IP Insights Inputs

A
  • user names, account IDs can be fed in directly
  • training channel, optional validation (computes AUC)
  • CSV only
    • entity, IP
51
Q

IP Insights Usage

A
  • neural network to learn about latent vector representations of entities and IP
  • entities hashed and embedded
    • need big enough hash size
  • auto generates negative samples by randomly pairing entities and IPs

HPs: # of entity vectors (hash size), vector dim, epochs, learning rate, batch size

CPU or GPU (GPU recommended)

AWS ML Exam (1 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions